INDEX

Explanations

phrases related to active engagement and participation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GDK

-0.18

urr

-0.16

ics

-0.15

ä¸ĺ

-0.15

icer

-0.15

anos

-0.14

quarters

-0.14

æĹıèĩªæ²»

-0.14

 Milk

-0.14

ict

-0.14

POSITIVE LOGITS

-duty

0.17

chia

0.16

vsp

0.16

ëŁ¬ìĬ¤

0.15

 duty

0.15

 Kurt

0.15

Ste

0.14

itch

0.14

ngle

0.14

orst

0.14

Activations Density 0.026%

phrases related to active engagement and participation

No Comments

No Known Activations